# Instruct-ICL: Instruction-Guided In-Context Learning for Post-Disaster Damage Assessment

arXiv: https://arxiv.org/abs/2605.11439 · HTML: https://mlsanity.com/paper/2605.11439/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 12 of 12)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding](https://mlsanity.com/paper/2012.02951/) (2020)
- [RescueNet: A High Resolution UAV Semantic Segmentation Benchmark Dataset for Natural Disaster Damage Assessment](https://mlsanity.com/paper/2202.12361/) (2022)
- [The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning](https://mlsanity.com/paper/2504.05081/) (2025)
- [Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination](https://mlsanity.com/paper/2411.12591/) (2024)
- [Visual Question Answering on Image Sets](https://mlsanity.com/paper/2008.11976/) (2020)
- [RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering](https://mlsanity.com/paper/2508.07918/) (2025)
- [Evaluating Numerical Reasoning in Text-to-Image Models](https://mlsanity.com/paper/2406.14774/) (2024)
- [DamageCAT: A Deep Learning Transformer Framework for Typology-Based Post-Disaster Building Damage Categorization](https://mlsanity.com/paper/2504.11637/) (2025)
- [ZeShot-VQA: Zero-Shot Visual Question Answering Framework with Answer Mapping for Natural Disaster Damage Assessment](https://mlsanity.com/paper/2506.00238/) (2025)
- [Deploying Rapid Damage Assessments from sUAS Imagery for Disaster Response](https://mlsanity.com/paper/2511.03132/) (2025)
- [Think First, Assign Next (ThiFAN-VQA): A Two-stage Chain-of-Thought Framework for Post-Disaster Damage Assessment](https://mlsanity.com/paper/2511.19557/) (2025)

## Abstract (arXiv)

Rapid and accurate situational awareness is essential for effective response during natural disasters, where delays in analysis can significantly hinder decision-making. Training task-specific models for post-disaster assessment is often time-consuming and computationally expensive, making such approaches impractical in time-critical scenarios. Consequently, pretrained multimodal large language models (MLLMs) have emerged as a promising alternative for post-disaster visual question answering (VQA), a task that aims to answer structured questions about visual scenes by jointly reasoning over images and text. While these models demonstrate strong multimodal reasoning capabilities, their responses can be sensitive to prompt formulation, which can limit their reliability in real-world disaster assessment scenarios. In this paper, we investigate whether structured reasoning strategies can improve the reliability of pretrained MLLMs for post-disaster VQA. Specifically, we explore multiple prompting paradigms in which one MLLM is used to generate task-specific instructions that serve as Chain-of-Thought (CoT) guidance for a second MLLM. These instructions are incorporated during answer generation with varying degrees of in-context learning (ICL), enabling the model to leverage both explicit reasoning guidance and contextual examples. We conduct our evaluation on the FloodNet dataset and compare these approaches against a zero-shot baseline. Our results demonstrate that integrating instruction-driven CoT reasoning consistently improves answer accuracy.